"OpenAI announced they are extending the Responses API to make it easier for developers to build agentic workflows, adding support for a shell tool, a built-in agent execution loop, a hosted container workspace, context compaction, and reusable agent skills."
"The execution loop can leverage the new Shell tool to interact with a computer via the command line, allowing it to carry out tasks using familiar Unix utilities like grep, curl, and awk, all available out of the box, and other programs."
"In addition to the Shell tool, OpenAI is also bundling a containerized execution environment where files and databases can live, with network access safely managed through policy controls."
OpenAI has enhanced the Responses API to facilitate agentic workflows by introducing a shell tool, an agent execution loop, and a hosted container workspace. Developers can now utilize a built-in infrastructure to manage tasks without creating their own execution environments. The agent execution loop allows the model to propose actions iteratively, executing them in a controlled environment. The new Shell tool expands capabilities beyond Python, enabling the execution of various programming languages. Additionally, a containerized execution environment is provided for safe file and database management.
Read at InfoQ
Unable to calculate read time
Collection
[
|
...
]